{
  "best_metric": 0.5544013381004333,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 3.1216216216216215,
  "eval_steps": 25,
  "global_step": 42,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 47.21583557128906,
      "learning_rate": 5e-05,
      "loss": 24.3667,
      "step": 1
    },
    {
      "epoch": 0.07207207207207207,
      "eval_loss": 0.8149463534355164,
      "eval_runtime": 4.7508,
      "eval_samples_per_second": 10.524,
      "eval_steps_per_second": 2.736,
      "step": 1
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 57.1197509765625,
      "learning_rate": 0.0001,
      "loss": 25.3377,
      "step": 2
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 41.60649871826172,
      "learning_rate": 9.986128001799077e-05,
      "loss": 23.8775,
      "step": 3
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 20.195768356323242,
      "learning_rate": 9.94459753267812e-05,
      "loss": 20.0562,
      "step": 4
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 18.211320877075195,
      "learning_rate": 9.875664641789545e-05,
      "loss": 19.7096,
      "step": 5
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 19.43238067626953,
      "learning_rate": 9.779754323328192e-05,
      "loss": 18.9009,
      "step": 6
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 15.369427680969238,
      "learning_rate": 9.657457896300791e-05,
      "loss": 18.4295,
      "step": 7
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 14.130334854125977,
      "learning_rate": 9.509529358847655e-05,
      "loss": 18.7928,
      "step": 8
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 13.11184310913086,
      "learning_rate": 9.336880739593416e-05,
      "loss": 18.8276,
      "step": 9
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 13.946846008300781,
      "learning_rate": 9.140576474687264e-05,
      "loss": 17.3055,
      "step": 10
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 11.439675331115723,
      "learning_rate": 8.921826845200139e-05,
      "loss": 18.0607,
      "step": 11
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 11.935064315795898,
      "learning_rate": 8.681980515339464e-05,
      "loss": 18.4346,
      "step": 12
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 12.615089416503906,
      "learning_rate": 8.422516217485826e-05,
      "loss": 18.0111,
      "step": 13
    },
    {
      "epoch": 1.0405405405405406,
      "grad_norm": 10.806593894958496,
      "learning_rate": 8.14503363531613e-05,
      "loss": 17.5144,
      "step": 14
    },
    {
      "epoch": 1.1126126126126126,
      "grad_norm": 11.201070785522461,
      "learning_rate": 7.85124354122177e-05,
      "loss": 16.3934,
      "step": 15
    },
    {
      "epoch": 1.1846846846846848,
      "grad_norm": 10.916080474853516,
      "learning_rate": 7.542957248827961e-05,
      "loss": 16.3291,
      "step": 16
    },
    {
      "epoch": 1.2567567567567568,
      "grad_norm": 10.406458854675293,
      "learning_rate": 7.222075445642904e-05,
      "loss": 15.7544,
      "step": 17
    },
    {
      "epoch": 1.3288288288288288,
      "grad_norm": 10.540088653564453,
      "learning_rate": 6.890576474687263e-05,
      "loss": 16.6168,
      "step": 18
    },
    {
      "epoch": 1.400900900900901,
      "grad_norm": 11.303304672241211,
      "learning_rate": 6.550504137351576e-05,
      "loss": 16.2968,
      "step": 19
    },
    {
      "epoch": 1.472972972972973,
      "grad_norm": 12.154343605041504,
      "learning_rate": 6.203955092681039e-05,
      "loss": 15.4487,
      "step": 20
    },
    {
      "epoch": 1.545045045045045,
      "grad_norm": 10.309591293334961,
      "learning_rate": 5.8530659307753036e-05,
      "loss": 15.9695,
      "step": 21
    },
    {
      "epoch": 1.6171171171171173,
      "grad_norm": 10.977252006530762,
      "learning_rate": 5.500000000000001e-05,
      "loss": 16.1751,
      "step": 22
    },
    {
      "epoch": 1.689189189189189,
      "grad_norm": 11.167401313781738,
      "learning_rate": 5.1469340692246995e-05,
      "loss": 15.5987,
      "step": 23
    },
    {
      "epoch": 1.7612612612612613,
      "grad_norm": 9.518537521362305,
      "learning_rate": 4.7960449073189606e-05,
      "loss": 14.9223,
      "step": 24
    },
    {
      "epoch": 1.8333333333333335,
      "grad_norm": 10.986368179321289,
      "learning_rate": 4.4494958626484276e-05,
      "loss": 16.8295,
      "step": 25
    },
    {
      "epoch": 1.8333333333333335,
      "eval_loss": 0.5544013381004333,
      "eval_runtime": 4.8104,
      "eval_samples_per_second": 10.394,
      "eval_steps_per_second": 2.702,
      "step": 25
    },
    {
      "epoch": 1.9054054054054053,
      "grad_norm": 10.637453079223633,
      "learning_rate": 4.109423525312738e-05,
      "loss": 15.3613,
      "step": 26
    },
    {
      "epoch": 2.009009009009009,
      "grad_norm": 11.018033027648926,
      "learning_rate": 3.777924554357096e-05,
      "loss": 15.2808,
      "step": 27
    },
    {
      "epoch": 2.081081081081081,
      "grad_norm": 9.55007553100586,
      "learning_rate": 3.45704275117204e-05,
      "loss": 14.7026,
      "step": 28
    },
    {
      "epoch": 2.153153153153153,
      "grad_norm": 10.30716609954834,
      "learning_rate": 3.1487564587782306e-05,
      "loss": 14.6719,
      "step": 29
    },
    {
      "epoch": 2.225225225225225,
      "grad_norm": 10.953435897827148,
      "learning_rate": 2.854966364683872e-05,
      "loss": 13.8655,
      "step": 30
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 10.068406105041504,
      "learning_rate": 2.577483782514174e-05,
      "loss": 14.6353,
      "step": 31
    },
    {
      "epoch": 2.3693693693693696,
      "grad_norm": 11.066611289978027,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 14.7031,
      "step": 32
    },
    {
      "epoch": 2.4414414414414414,
      "grad_norm": 11.900208473205566,
      "learning_rate": 2.0781731547998614e-05,
      "loss": 14.1224,
      "step": 33
    },
    {
      "epoch": 2.5135135135135136,
      "grad_norm": 10.959716796875,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 13.9909,
      "step": 34
    },
    {
      "epoch": 2.5855855855855854,
      "grad_norm": 11.068878173828125,
      "learning_rate": 1.6631192604065855e-05,
      "loss": 14.7811,
      "step": 35
    },
    {
      "epoch": 2.6576576576576576,
      "grad_norm": 11.743328094482422,
      "learning_rate": 1.490470641152345e-05,
      "loss": 13.8688,
      "step": 36
    },
    {
      "epoch": 2.72972972972973,
      "grad_norm": 11.463229179382324,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 13.4959,
      "step": 37
    },
    {
      "epoch": 2.801801801801802,
      "grad_norm": 11.082849502563477,
      "learning_rate": 1.2202456766718093e-05,
      "loss": 14.5614,
      "step": 38
    },
    {
      "epoch": 2.873873873873874,
      "grad_norm": 11.691807746887207,
      "learning_rate": 1.1243353582104556e-05,
      "loss": 13.9716,
      "step": 39
    },
    {
      "epoch": 2.945945945945946,
      "grad_norm": 12.260763168334961,
      "learning_rate": 1.0554024673218807e-05,
      "loss": 12.9331,
      "step": 40
    },
    {
      "epoch": 3.0495495495495497,
      "grad_norm": 10.715076446533203,
      "learning_rate": 1.0138719982009242e-05,
      "loss": 13.9412,
      "step": 41
    },
    {
      "epoch": 3.1216216216216215,
      "grad_norm": 10.816911697387695,
      "learning_rate": 1e-05,
      "loss": 13.9132,
      "step": 42
    }
  ],
  "logging_steps": 1,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.7651148387896525e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}